Team Of Agents Research Articles

Locating a black hole in a dynamic ring

In networked environments supporting mobile agents, a pressing problem is the presence of network sites harmful for the agents. In this paper we consider the danger posed by a node that destroys any incoming agent without leaving any trace. Such a dangerous node is known in the literature as a black hole (Bh). The problem of a team of system agents determining its location, known as black hole search (Bhs ), has been extensively studied in the literature under a variety of assumptions, both in synchronous and asynchronous settings. The main complexity parameter of Bhsis the number of system agents (called size) needed to solve the problem; other parameters are the number of moves (called cost) performed by the agents, and the time until termination.In the existing literature, with only a couple of exceptions, all results are based on a common assumption that the network is static, i.e. its topology does not change in time. We consider instead the Bhswhen the network is dynamic: the link structure of the graph changes over time. While time-varying graphs have been the focus of intense research in the last two decades, very little is known on the problem of locating the Bh in such networks.In this paper, we contribute to fill this research gap by studying Bhsin dynamic ring networks, focusing on the 1-interval connectivity adversarial dynamics. Feasibility and complexity of the problem depend on many factors, specifically on the size n of the ring, whether or not n is known, and the type of inter-agent communication (whiteboards, tokens, face-to-face, visual). In this paper, we provide a complete feasibility characterization presenting size optimal algorithms. Furthermore, we establish lower bounds on the cost and time of size-optimal solutions and show that our algorithms achieve those bounds.

Complex Laplacian approach for formation tracking without velocity measurements

This paper is focused on formation tracking control of multi-agent systems in a leader–follower setting. The objective is to introduce control algorithms to steer a team of mobile agents into a desired, moving geometrical pattern while the agents are unaware of their own and other agents' velocity information during the entire process. We introduce a formation control law under which the agents asymptotically shape a desired geometrical pattern and track a constant reference velocity. Another control law is then introduced to address the case where the reference velocity is time-varying. Both control laws are based on the complex Laplacian approach and do not require agents' velocity information. The convergence of these algorithms are proved and their performance are examined via numerical examples. Simulation results verify the outperformance of the proposed control laws compared to the rival control schemes in the literature.

USE OF CONSTRUCTION INCENTIVE: SECTORAL DIFFERENCES

Incentive contracting has been developed to motivate agent teams to render extra effort. Typically, three types of incentive arrangements have been used: incentive/penalty for superior/under performance; risk/reward sharing; and future business opportunities. This study found that there are significant differences in the choice of incentive arrangements between private and public projects in Hong Kong. It is uncommon for public projects to use future business as a performance incentivizer, whereas private developers often signal repeated business together with heavy penalties to tie with their contractors. This study further identified various attributes affecting the use of incentives in both private and public engineering sectors of Hong Kong. The respective preferences were unveiled through a literature review, semi-structured interviews with industry experts, and a survey. The findings reveal that the public and private sectors consider the implementation issues regarding various performance targets critical to the type of incentives to be used. Whilst the primary concern of the public sector is accountability, the private sector is skeptical about the need to provide extra for the contractors for what they have already contracted for.

USE OF CONSTRUCTION INCENTIVE: SECTORAL DIFFERENCES

Incentive contracting has been developed to motivate agent teams to render extra effort. Typically, three types of incentive arrangements have been used: incentive/penalty for superior/under performance; risk/reward sharing; and future business opportunities. This study found that there are significant differences in the choice of incentive arrangements between private and public projects in Hong Kong. It is uncommon for public projects to use future business as a performance incentivizer, whereas private developers often signal repeated business together with heavy penalties to tie with their contractors. This study further identified various attributes affecting the use of incentives in both private and public engineering sectors of Hong Kong. The respective preferences were unveiled through a literature review, semi-structured interviews with industry experts, and a survey. The findings reveal that the public and private sectors consider the implementation issues regarding various performance targets critical to the type of incentives to be used. Whilst the primary concern of the public sector is accountability, the private sector is skeptical about the need to provide extra for the contractors for what they have already contracted for.

Effects of Explanation Types on User Satisfaction and Performance in Human-agent Teams

Automated agents, with rapidly increasing capabilities and ease of deployment, will assume more key and decisive roles in our societies. We will encounter and work together with such agents in diverse domains and even in peer roles. To be trusted and for seamless coordination, these agents would be expected and required to explain their decision making, behaviors, and recommendations. We are interested in developing mechanisms that can be used by human-agent teams to maximally leverage relative strengths of human and automated reasoners. We are interested in ad hoc teams in which team members start to collaborate, often to respond to emergencies or short-term opportunities, without significant prior knowledge about each other. In this study, we use virtual ad hoc teams, consisting of a human and an agent, collaborating over a few episodes where each episode requires them to complete a set of tasks chosen from available task types. Team members are initially unaware of the capabilities of their partners for the available task types, and the agent task allocator must adapt the allocation process to maximize team performance. It is important in collaborative teams of humans and agents to establish user confidence and satisfaction, as well as to produce effective team performance. Explanations can increase user trust in agent team members and in team decisions. The focus of this paper is on analyzing how explanations of task allocation decisions can influence both user performance and the human workers’ perspective, including factors such as motivation and satisfaction. We evaluate different types of explanation, such as positive, strength-based explanations and negative, weakness-based explanations, to understand (a) how satisfaction and performance are improved when explanations are presented, and (b) how factors such as confidence, understandability, motivation, and explanatory power correlate with satisfaction and performance. We run experiments on the CHATboard platform that allows virtual collaboration over multiple episodes of task assignments, with MTurk workers. We present our analysis of the results and conclusions related to our research hypotheses.

Impact of Task Constraint on Agent Team Size of Self-Organizing Systems Measured by Effective Entropy

Impact of Task Constraint on Agent Team Size of Self-Organizing Systems Measured by Effective Entropy

Traffic Flow Optimisation for Lifelong Multi-Agent Path Finding

Multi-Agent Path Finding (MAPF) is a fundamental problem in robotics that asks us to compute collision-free paths for a team of agents, all moving across a shared map. Although many works appear on this topic, all current algorithms struggle as the number of agents grows. The principal reason is that existing approaches typically plan free-flow optimal paths, which creates congestion. To tackle this issue, we propose a new approach for MAPF where agents are guided to their destination by following congestion-avoiding paths. We evaluate the idea in two large-scale settings: one-shot MAPF, where each agent has a single destination, and lifelong MAPF, where agents are continuously assigned new destinations. Empirically, we report large improvements in solution quality for one-short MAPF and in overall throughput for lifelong MAPF.

Mean-Field Multiagent Reinforcement Learning: A Decentralized Network Approach

One of the challenges for multiagent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. Whereas exciting progress has been made to analyze decentralized MARL with the network of agents for social networks and team video games, little is known theoretically for decentralized MARL with the network of states for modeling self-driving vehicles, ride-sharing, and data and traffic routing. This paper proposes a framework of localized training and decentralized execution to study MARL with the network of states. Localized training means that agents only need to collect local information in their neighboring states during the training phase; decentralized execution implies that agents can execute afterward the learned decentralized policies, which depend only on agents’ current states. The theoretical analysis consists of three key components: the first is the reformulation of the MARL system as a networked Markov decision process with teams of agents, enabling updating the associated team Q-function in a localized fashion; the second is the Bellman equation for the value function and the appropriate Q-function on the probability measure space; and the third is the exponential decay property of the team Q-function, facilitating its approximation with efficient sample efficiency and controllable error. The theoretical analysis paves the way for a new algorithm LTDE-Neural-AC, in which the actor–critic approach with overparameterized neural networks is proposed. The convergence and sample complexity are established and shown to be scalable with respect to the sizes of both agents and states. To the best of our knowledge, this is the first neural network–based MARL algorithm with network structure and provable convergence guarantee. Funding: X. Wei is partially supported by NSFC no. 12201343. R. Xu is partially supported by the NSF CAREER award DMS-2339240.

Towards a Natural Language Interface for Flexible Multi-Agent Task Assignment

Task assignment and scheduling algorithms are powerful tools for autonomously coordinating large teams of robotic or AI agents. However, the decisions these system make often rely on components designed by domain experts, which can be difficult for non-technical end-users to understand or modify to their own ends. In this paper we propose a preliminary design for a flexible natural language interface for a task assignment system. The goal of our approach is both to grant users more control over a task assignment system's decision process, as well as render these decisions more transparent. Users can direct the task assignment system via natural language commands, which are applied as constraints to a mixed-integer linear program (MILP) using a large language model (LLM). Additionally, our proposed system can alert users to potential issues with their commands, and engage them in a corrective dialogue in order to find a viable solution. We conclude with a description of our planned user-evaluation in the simulated environment Overcooked and describe next steps towards developing a flexible and transparent task allocation system.

The Illicit Trade in Cultural Objects in Tanzania: An Investigative Report

Investigators are an important apparatus in tackling highly organized crimes committed in a state of high confidentiality. In Africa, surveillance techniques are commonly used to expose many crimes including serious offences against individuals or a society. However, ethnographic objects and other cultural remains have received less investigative attention, and as the result they have been illegally exported out of the continent for economic benefits. Ethnographic objects refer to objects made, modified or used by humans that collectively represent cultural references and they are protected by law, rules, or customs. Cultural remains refer to tangible movable objects made, shaped, painted, sculptured, inscribed, and produced or modified by human agency. In Tanzania, like in many other African countries, relics and ethnographic objects have been plundered and illegally traded in underground economy across the world. People engaged in trading of ethnographic objects use souvenir markets as decoys and shipping passage to send goods abroad. This article presents the results from a recent investigation conducted at one of the souvenir markets in Mwenge, Dar es Salaam, Tanzania, where cultural relics and ethnographic objects from Tanzania and other African countries have been brought together and shipped abroad for commercial interests. A joint team of undercover intelligence agents and key informants participated in a confidential work to investigate the process by which ethnographic objects are collected, marketed and distributed to local and foreign markets. Mwenge is one of the largest and most popular souvenir centers with large and unique artefacts shops operating as tourism attractions. During this investigation, which spanned six months, our team identified 530 ethnographic objects which were on the market, ready to be sold and exported, despite their legal status under Tanzanian law, according to which their sale and export are unlawful. This study revealed that people who are engaged in the illicit trading activities of relics and ethnographic objects are knowledgeable, use legitimate business license, collection- and export permits to conceal their illicit trade of ethnographic objects. Furthermore, they are aware of the poor monitoring institutions and the illiteracy among security officials at ports of exits. This article discloses some of the techniques used to conceal the trafficking of cultural objects in Tanzania and proposes suitable measures to counter the problem.

Positive and negative explanation effects in human–agent teams

Positive and negative explanation effects in human–agent teams

Generating Task Reallocation Suggestions to Handle Contingencies in Human-Supervised Multi-Robot Missions

In a mission with significant uncertainty due to intermittent communications, delayed information flow, and robotic failures, the role of human supervisors is extremely challenging. As and when any new information arrives, humans must infer both the existing and predicted future states, identify potential contingencies, and update task assignments to robots rapidly. We propose methodologies for automated generation of task reallocation suggestions to humans to assist in the decision-making process. Our generated robot retasking plan minimizes a modified makespan of the mission, which incorporates task criticality and penalty for incomplete tasks. The plan considers the effects of potential mission contingencies on the tasks, the robots, and the future performance of the robots operating based on the previous task plans. Our method includes the incorporation of two optional tasks, i.e., relay and robot rescue, for performance improvement. The rescue task has probabilistic outcomes affecting the team size. One or more rescues are incorporated in a way that can minimize the expected value of the modified makespan overall possibilities of rescue outcomes. We have conducted performance evaluation using simulation, demonstrating the value of the optional tasks and performance enhancement using our method of incorporating them. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The work reported in this paper will be useful in applications where a team of agents is deployed to carry on a large-scale mission with communication constraints where the number of functional agents can change probabilistically. Typically, such uncertainty is encountered in applications that are challenging or dangerous in nature. Agents can have non-zero probabilities to fail while doing certain risky tasks and to get recovered by other agents. The proposed centralized multi-agent task reallocation method can help in proactively addressing potential contingencies in surveillance, search and rescue, or disaster relief to support resilient operations while having a supervisor in the higher chain of command.

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Human–Agent Team Dynamics: A Review and Future Research Opportunities

Interpretable Learned Emergent Communication for Human–Agent Teams

Learning interpretable communication is essential for multi-agent and human-agent teams (HATs). In multi-agent reinforcement learning for partially-observable environments, agents may convey information to others via learned communication, allowing the team to complete its task. Inspired by human languages, recent works study discrete (using only a finite set of tokens) and sparse (communicating only at some time-steps) communication. However, the utility of such communication in human-agent team experiments has not yet been investigated. In this work, we analyze the efficacy of sparse-discrete methods for producing emergent communication that enables high agent-only and human-agent team performance. We develop agent-only teams that communicate sparsely via our scheme of Enforcers that sufficiently constrain communication to any budget. Our results show no loss or minimal loss of performance in benchmark environments and tasks. In human-agent teams tested in benchmark environments, where agents have been modeled using the Enforcers, we find that a prototype-based method produces meaningful discrete tokens that enable human partners to learn agent communication faster and better than a one-hot baseline. Additional HAT experiments show that an appropriate sparsity level lowers the cognitive load of humans when communicating with teams of agents and leads to superior team performance.

Multiagent, Multitarget Path Planning in Markov Decision Processes

Missions for autonomous systems often require agents to visit multiple targets in complex operating conditions. This work considers the problem of visiting a set of targets in minimum time by a team of non-communicating agents in a Markov decision process (MDP). The single-agent problem is at least NP-complete by reducing it to a Hamiltonian path problem. We first discuss an optimal algorithm based on Bellman's optimality equation that is exponential in the number of target states. Then, we trade-off optimality for time complexity by presenting a suboptimal algorithm that is polynomial at each time step. We prove that the proposed algorithm generates optimal policies for certain classes of MDPs. Extending our procedure to the multi-agent case, we propose a target partitioning algorithm that approximately minimizes the expected time to visit the targets. We prove that our algorithm generates optimal partitions for clustered target scenarios. We present the performance of our algorithms on random MDPs and gridworld environments inspired by ocean dynamics. We show that our algorithms are much faster than the optimal procedure and more optimal than the currently available heuristic.

Analysis and Requirement Generation for Defense Intelligence Search: Addressing Data Overload through Human–AI Agent System Design for Ambient Awareness

This research addresses the data overload faced by intelligence searchers in government and defense agencies. The study leverages methods from the Cognitive Systems Engineering (CSE) literature to generate insights into the intelligence search work domain. These insights are applied to a supporting concept and requirements for designing and evaluating a human-AI agent team specifically for intelligence search tasks. Domain analysis reveals the dynamic nature of the ‘value structure’, a term that describes the evolving set of criteria governing the intelligence search process. Additionally, domain insight provides details for search aggregation and conceptual spaces from which the value structure could be efficiently applied for intelligence search. Support system designs that leverage these findings may enable an intelligence searcher to interact with and understand data at more abstract levels to improve task efficiency. Additionally, new system designs can support the searcher by facilitating an ‘Ambient Awareness’ of non-selected objects in a large data field through relevant system cues. Ambient Awareness achieved through the supporting concept and AI teaming has the potential to address the data overload problem while increasing the breadth and depth of search coverage.

RGS⊕\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\oplus $$\\end{document}: RDF graph synchronization for collaborative robotics

In the context of collaborative robotics, distributed situation awareness is essential for supporting collective intelligence in teams of robots and human agents where it can be used for both individual and collective decision support. This is particularly important in applications pertaining to emergency rescue and crisis management. During operational missions, data and knowledge is gathered incrementally and in different ways by heterogeneous robots and humans. The purpose of this paper is to describe an RDF Graph Synchronization System called RGS⊕\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\oplus $$\\end{document}. It is assumed that a dynamic set of agents provide or retrieve knowledge stored in their local RDF Graphs which are continuously synchronized between agents. The RGS⊕\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\oplus $$\\end{document} System was designed to handle unreliable communication and does not rely on a static centralized infrastructure. It is capable of synchronizing knowledge as timely as possible and allows agents to access knowledge while it is incrementally acquired. A deeper empirical analysis of the RGS⊕\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\oplus $$\\end{document} System is provided that shows both its efficiency and efficacy.

STEM education institutional change projects: examining enacted approaches through the lens of the Four Categories of Change Strategies Model

BackgroundEnacting STEM education reform is a complex task and there are a variety of approaches that might be selected by change agents. When working on an institutional change project to impact multiple parts of the STEM education system, teams of change agents may select multiple strategies and tactics to enact at one time and over multiple years of a project. However, the literature lacks studies which document and analyze strategies and tactics used by change project teams in a way that can be useful for other change agents. The current study seeks to fill this gap by investigating National Science Foundation-funded change initiatives at three public research universities focused on encouraging the adoption of evidenced-based instructional practices by STEM faculty in order to understand the strategies used within and across projects.ResultsQualitative framework analysis using the lens of the Henderson et al. (Journal of Research in Science Teaching 48(8): 952–984, 2011. https://doi.org/10.1002/tea.20439) Four Categories of Change Strategies Model showed that institutional projects enact a wide range of tactics that span the four strategies represented in the four categories of the model both across institutions and within each institution. The analysis documents a number of change tactics not previously described by the model and offers expanded definitions of the change processes that operate within each category in the context of institutional change projects.ConclusionThis descriptive work advances our understanding of the breadth and depth of actions taken by institutional change initiatives and provides insights into types of variations that might be observed based on different institutional contexts. The current analysis both affirms the value of the original model and identifies expanded ways to think about the four categories within the context of institutional change projects.

Trochoidal patterns generation using generalized consensus strategy for double-integrator dynamic agents

This article studies a distributed consensus law to achieve a coordinated trochoidal formation among a team of mobile agents. The mobile agents are modeled as double integrators. We generalize an existing consensus algorithm for double-integrator dynamics (1) to achieve trochoidal patterns under a general network topology and (2) to extend the pattern formation in a 3-D plane. Since the trochoidal patterns are 2-D curves, the proposed control law allows us to specify the 2-D plane in the 3-D space on which the patterns will be formed. We modify the standard consensus protocol and manipulate the gains to create trochoidal motion through local information exchange by appropriately placing the eigenvalues of the system. Trochoids have been used in multifaceted robotic applications such as area coverage, hurricane sampling, and orbit designs for satellites, apart from their aesthetic appeal. Computer simulations and multi-robot experiments are presented to validate the theoretical findings.

Angle Rigidity for Multiagent Formations in 3-D

This paper establishes the notion and properties of angle rigidity for 3D multi-point frameworks with angle constraints, and then designs direction-only control laws to stabilize angle rigid formations of mobile agents in 3D. Angles are defined using the interior angles of triangles within the given framework, which are independent of the choice of coordinate frames and can be conveniently measured using monocular cameras and direction-finding arrays. We show that 3D angle rigidity is a local property, which is in contrast to the 3D bearing rigidity as has been proved to be a global property in the literature. We demonstrate that such angle rigid and globally angle rigid frameworks can be constructed through adding repeatedly new points to the original small angle rigid framework with carefully chosen angle constraints. We also investigate how to merge two 3D angle rigid frameworks by connecting three points of one angle rigid framework simultaneously to the other. When angle constraints are given only in the surface of a framework, angle rigidity of convex polyhedra is studied, in which the cases of triangular face and triangulated face are considered, respectively. The proposed 3D angle rigidity theory is then utilized to design decentralized formation control strategies using local direction measurements for teams of mobile agents. Simulation examples are provided to validate the convergence of the formations.